Training in progress, step 4330, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1657
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f7e03b2472a61dfa70341b5815e92e3a6fe7f9afcdab3889cfdb4b8f8514fe1
|
| 3 |
size 1657
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14709
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:72ecb6d5c61a630be1d963252ea9f2bd60d6d60f034105d24723ef95be1adff4
|
| 3 |
size 14709
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fbcb6d3f62916b01587182465cd935222d1396eff8e87cbb1a2e8fc5ef134b33
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 33.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -7784,6 +7784,24 @@
|
|
| 7784 |
"mean_token_accuracy": 0.6541249454021454,
|
| 7785 |
"num_tokens": 15755018.0,
|
| 7786 |
"step": 4320
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7787 |
}
|
| 7788 |
],
|
| 7789 |
"logging_steps": 5,
|
|
@@ -7803,7 +7821,7 @@
|
|
| 7803 |
"attributes": {}
|
| 7804 |
}
|
| 7805 |
},
|
| 7806 |
-
"total_flos":
|
| 7807 |
"train_batch_size": 4,
|
| 7808 |
"trial_name": null,
|
| 7809 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 33.30769230769231,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4330,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 7784 |
"mean_token_accuracy": 0.6541249454021454,
|
| 7785 |
"num_tokens": 15755018.0,
|
| 7786 |
"step": 4320
|
| 7787 |
+
},
|
| 7788 |
+
{
|
| 7789 |
+
"epoch": 33.26923076923077,
|
| 7790 |
+
"grad_norm": 0.0,
|
| 7791 |
+
"learning_rate": 2.8380000000000003e-05,
|
| 7792 |
+
"loss": 1.6412,
|
| 7793 |
+
"mean_token_accuracy": 0.665298554301262,
|
| 7794 |
+
"num_tokens": 15774342.0,
|
| 7795 |
+
"step": 4325
|
| 7796 |
+
},
|
| 7797 |
+
{
|
| 7798 |
+
"epoch": 33.30769230769231,
|
| 7799 |
+
"grad_norm": 0.0,
|
| 7800 |
+
"learning_rate": 2.8355000000000002e-05,
|
| 7801 |
+
"loss": 1.7192,
|
| 7802 |
+
"mean_token_accuracy": 0.6550895661115647,
|
| 7803 |
+
"num_tokens": 15792876.0,
|
| 7804 |
+
"step": 4330
|
| 7805 |
}
|
| 7806 |
],
|
| 7807 |
"logging_steps": 5,
|
|
|
|
| 7821 |
"attributes": {}
|
| 7822 |
}
|
| 7823 |
},
|
| 7824 |
+
"total_flos": 8.003320026719846e+17,
|
| 7825 |
"train_batch_size": 4,
|
| 7826 |
"trial_name": null,
|
| 7827 |
"trial_params": null
|